Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach

arXiv:2403.11380v1 Announce Type: new
Abstract: Supernet is a core component in many recent Neural Architecture Search (NAS) methods. It not only helps embody the search space but also provides a (relative) estimation of the final performance of candidate architectures. Thus, it is critical that the top architectures ranked by a supernet should be consistent with those ranked by true performance, which is known as the order-preserving ability. In this work, we analyze the order-preserving ability on the whole search space …

abstract architecture architectures arxiv boosting core cs.cv fine-tuning nas neural architecture search performance search space type